Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5936 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1626. Min Act: -0.0002

Data Index: 333442 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1762. Min Act: -0.0002

Data Index: 1217013 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1718. Min Act: -0.0002

Data Index: 685640 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1769. Min Act: -0.0002

Data Index: 723368 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1627. Min Act: -0.0002

Data Index: 1126440 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1659. Min Act: -0.0002

Data Index: 792796 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1594. Min Act: -0.0002

Data Index: 542339 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1533. Min Act: -0.0002

Data Index: 232634 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1628. Min Act: -0.0002

Data Index: 4615 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1617. Min Act: -0.0002

Data Index: 1182432 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1646. Min Act: -0.0002

Data Index: 568560 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1564. Min Act: -0.0002

Data Index: 989449 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1615. Min Act: -0.0002

Data Index: 14007 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1533. Min Act: -0.0002

Data Index: 1304324 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1534. Min Act: -0.0002

Data Index: 156506 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1488. Min Act: -0.0002

Data Index: 639115 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1482. Min Act: -0.0002

Data Index: 1126104 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1497. Min Act: -0.0002

Data Index: 253247 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1484. Min Act: -0.0002

Data Index: 411092 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1537. Min Act: -0.0002

Data Index: 265885 (C4 (Web Text))

Max Activating Token Index: 162